canicode: Command for Claude Code

.claude/commands/review-run.md

review-run is a command for Claude Code from let-sunny/canicode. It costs 0 tokens per session (784 once invoked), scanned A, original, MIT.

A review command for examining a completed development pipeline run. It reads the run’s records and compares the implementation with the plan and code changes.

In plain words
What is it for?
Use it to review an automated development run, check whether tasks match the issue, assess risks and plan quality, and inspect the resulting branch changes.
Why use it?
It gathers pipeline status, planning details, implementation decisions, and the actual diff in one quality assessment.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is let-sunny/canicode's own configuration. It tells Claude Code how to work on canicode itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything canicode configures →

Part of the canicode plugin — 3 skills, 3 commands, 3 hooks, 2 MCP servers shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to let-sunny/canicode. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/let-sunny/canicode/main/.claude/commands/review-run.md
Clone the repo
git clone --depth 1 https://github.com/let-sunny/canicode

Made for: Claude Code.

Or install canicode, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 3 hooks, 2 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-run

README.md
[![agentmods](https://agentmods.dev/badge/commands/let-sunny/canicode/review-run.svg)](https://agentmods.dev/commands/let-sunny/canicode/review-run)
Your own site
<a href="https://agentmods.dev/commands/let-sunny/canicode/review-run"><img src="https://agentmods.dev/badge/commands/let-sunny/canicode/review-run.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 784 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00784
Opus 5 $0.00000 $0.00392
Sonnet 5 $0.00000 $0.00157
Haiku 4.5 $0.00000 $0.00078

Measured 8d ago against content hash eb67f6958218, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-run scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/review-run.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review a completed /develop pipeline run and provide a structured QA assessment.

Input: $ARGUMENTS (run directory path, e.g. logs/develop/253--2026-04-16-0903)

Instructions

Step 1 — Pipeline Overview

Read $ARGUMENTS/index.json and summarize:

  • Issue number, title, branch
  • Pipeline status (completed / failed / partial)
  • Each step's status, duration, and retry count
  • Total pipeline duration

If index.json is missing, stop and report: "Not a valid run directory."

Step 2 — Plan Quality

Read $ARGUMENTS/plan.json and assess:

  • Are the tasks well-scoped and aligned with the issue?
  • Are designDecisions reasonable and well-justified?
  • Are risks identified and realistic?
  • Does split / remainingDescription make sense for the issue size?

Step 3 — Implementation Review

Read $ARGUMENTS/implement-log.json for decisions and knownRisks. Read $ARGUMENTS/implement-output.txt for agent output context.

Then run the actual diff to see what changed:

git diff main...<branch>

Use the branch field from index.json. If the branch no longer exists (e.g., merged and deleted), note this and skip the diff.

Assess:

  • Do the changes match the plan's tasks?
  • Are the implementer's decisions sound?
  • Are the knownRisks legitimate concerns?
  • Does the diff look clean — no unrelated changes, no leftover debug code?

Step 4 — Test Results

Read $ARGUMENTS/test-result.json (may not exist if test was skipped).

If it exists, check whether lint and tests passed or what failed.

Step 5 — Self-Review Findings

Read $ARGUMENTS/review.json and assess:

  • Is the review verdict reasonable given the findings?
  • Are the findings legitimate issues or false positives?
  • Did the reviewer catch the implementer's knownRisks?
  • Are intentConflict flags used correctly?

Step 6 — Fix Coverage

Read $ARGUMENTS/fix-log.json (may not exist if fix was skipped).

If it exists, assess:

  • Did the fixer address all review findings?
  • For skipped findings: are the skip reasons justified?
  • Did the fix introduce any new concerns?

Read the full file on GitHub · 111 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 111 lines · 0 tokens per session scan A eb67f6958218

Subscribe to this mod's changes

review-run is a command published in the GitHub repository let-sunny/canicode (10 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 784 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.